Preliminary Full-Scale Tests of the Center for Automated Processing of Hardwoods’ Auto-Image Detection and Computer- Based Grading and Cutup System

Automated lumber grading and yield optimization using computer controlled saws will be plausible for hardwoods if and when lumber scanning systems can reliably identify all defects by type. Existing computer programs could then be used to grade the lumber, identify the best cut-up solution, and control the sawing machines. The potential value of a scanning grading system depends on the accuracy and reliability of the computer-assigned grades compared to the performance of human graders. The potential worth of any scanning cut-up system is largely dependent on the parts recovered compared to today’s standard rough mill processing systems. The Center for Automated Processing of Hardwoods’ (CAPH) scanning system is a color line-scan camera-based image processing system. We compared the system’s scanning-grader performance with the NHLA grades assigned by company graders. The scanning-grader results indicated that 4 of 15 company graded boards were graded too high. In total, 67 percent of the boards were manually misgraded. Initial results indicate that the CAPH system is missing small sections of some defects and is misclassifying some clear wood as defective. We also compared the CAPH system’s scanning-optimization system to a rip-first rough mill processing system. The scanning-optimization results indicated a potential increase in rough part yield of 5 percent might be realized with the CAPH system. Proceedings of CIFAC ’94, Atlanta, Georgia, August 23-24, 1994 Copyright © 1994 by Wood Machining Institute 163